| 1 |
#! /usr/bin/perl |
| 2 |
# |
| 3 |
# Copyright (c) 2007-2025, PostgreSQL Global Development Group |
| 4 |
# |
| 5 |
# src/backend/utils/mb/Unicode/UCS_to_EUC_JIS_2004.pl |
| 6 |
# |
| 7 |
# Generate UTF-8 <--> EUC_JIS_2004 code conversion tables from |
| 8 |
# "euc-jis-2004-std.txt" (http://x0213.org) |
| 9 |
|
| 10 |
use strict; |
| 11 |
use warnings FATAL => 'all'; |
| 12 |
|
| 13 |
use convutils; |
| 14 |
|
| 15 |
my $this_script = 'src/backend/utils/mb/Unicode/UCS_to_EUC_JIS_2004.pl'; |
| 16 |
|
| 17 |
# first generate UTF-8 --> EUC_JIS_2004 table |
| 18 |
|
| 19 |
my $in_file = "euc-jis-2004-std.txt"; |
| 20 |
|
| 21 |
open(my $in, '<', $in_file) || die("cannot open $in_file"); |
| 22 |
|
| 23 |
my @all; |
| 24 |
|
| 25 |
while (my $line = <$in>) |
| 26 |
{ |
| 27 |
if ($line =~ /^0x(\w+)\s*U\+(\w+)\+(\w+)\s*#\s*(\S.*)?\s*$/) |
| 28 |
{ |
| 29 |
|
| 30 |
# combined characters |
| 31 |
my ($c, $u1, $u2) = ($1, $2, $3); |
| 32 |
# The "\t \t" below is just to avoid insubstantial diffs. |
| 33 |
my $rest = "U+" . $u1 . "+" . $u2 . "\t \t" . $4; |
| 34 |
my $code = hex($c); |
| 35 |
my $ucs1 = hex($u1); |
| 36 |
my $ucs2 = hex($u2); |
| 37 |
|
| 38 |
push @all, |
| 39 |
{ |
| 40 |
direction => BOTH, |
| 41 |
ucs => $ucs1, |
| 42 |
ucs_second => $ucs2, |
| 43 |
code => $code, |
| 44 |
comment => $rest, |
| 45 |
f => $in_file, |
| 46 |
l => $. |
| 47 |
}; |
| 48 |
} |
| 49 |
elsif ($line =~ /^0x(\w+)\s*U\+(\w+)\s*#\s*(\S.*)?\s*$/) |
| 50 |
{ |
| 51 |
|
| 52 |
# non-combined characters |
| 53 |
my ($c, $u, $rest) = ($1, $2, "U+" . $2 . $3); |
| 54 |
my $ucs = hex($u); |
| 55 |
my $code = hex($c); |
| 56 |
|
| 57 |
next if ($code < 0x80 && $ucs < 0x80); |
| 58 |
|
| 59 |
push @all, |
| 60 |
{ |
| 61 |
direction => BOTH, |
| 62 |
ucs => $ucs, |
| 63 |
code => $code, |
| 64 |
comment => $rest, |
| 65 |
f => $in_file, |
| 66 |
l => $. |
| 67 |
}; |
| 68 |
} |
| 69 |
} |
| 70 |
close($in); |
| 71 |
|
| 72 |
print_conversion_tables($this_script, "EUC_JIS_2004", \@all); |